TEST #820 RESULTS
05/04/2025 - 12:29 PM
ACCELERATOR
MODEL
28.1
tokens/s
generation
1.58
sec
time to first token
832
tokens/s
prompt
245
LocalScore
HOW YOU STACK UP
Explore All ResultsQwen2.5 14B Instruct - Q4_K - Medium
SYSTEM
CPU
11th Gen Intel Core i7-11700F @ 2.50GHz (rocketlake)
RAM
31.9GB
OS
Windows
Kernel Release
10.0
Architecture
x86_64
Version
Cosmopolitan 3.9.7 MODE=x86_64
RUNTIME
Name
llamafile
Version
0.9.2
Commit Hash
a30b324
DETAILED RESULTS
TEST NAME
PROMPT
GENERATION
TTFT
pp1024+tg16
956
tokens/s
29.2
tokens/s
1.11
sec
pp4096+tg256
784
tokens/s
25.2
tokens/s
5.26
sec
pp2048+tg256
886
tokens/s
27.8
tokens/s
2.35
sec
pp2048+tg768
885
tokens/s
27.4
tokens/s
2.35
sec
pp1024+tg1024
953
tokens/s
28.7
tokens/s
1.11
sec
pp1280+tg3072
929
tokens/s
26.9
tokens/s
1.41
sec
pp384+tg1152
1002
tokens/s
29.0
tokens/s
417
ms
pp64+tg1024
805
tokens/s
29.2
tokens/s
144
ms
pp16+tg1536
285
tokens/s
29.2
tokens/s
90
ms